© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2455
    Prev
    Next
    INDEX
    Explanations

    how to ask questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apot
    -0.12
    çIJĨ解åĴĮ
    -0.11
    çľ·
    -0.10
    Dragon
    -0.09
    spo
    -0.09
    çĪ±å°Ķ
    -0.08
    æĬ«
    -0.08
    plet
    -0.08
    ystone
    -0.08
    apore
    -0.08
    POSITIVE LOGITS
    çĻ½æĸij
    0.09
    ellant
    0.09
     HOLDER
    0.09
    èĭ·
    0.09
    æĭ£
    0.09
    çĶ¨é¤IJ
    0.08
     Immutable
    0.08
    lee
    0.08
    ç´łé£Ł
    0.08
    ToF
    0.08
    Activations Density 0.040%

    No Known Activations